MONet: Multi-scale Overlap Network for Duplication Detection in Biomedical Images

TL;DR

This paper introduces MONet, a multi-scale overlap detection model designed to identify duplicated regions in biomedical images, addressing the unique challenges of biomedical image manipulation detection.

Contribution

The paper presents a novel hierarchical multi-scale model specifically tailored for biomedical image duplication detection, outperforming existing methods.

Findings

Achieves state-of-the-art performance on biomedical image duplication detection tasks.

Effectively detects duplicated regions across multiple biomedical image categories.

Reduces computational complexity by hierarchical patch analysis.

Abstract

Manipulation of biomedical images to misrepresent experimental results has plagued the biomedical community for a while. Recent interest in the problem led to the curation of a dataset and associated tasks to promote the development of biomedical forensic methods. Of these, the largest manipulation detection task focuses on the detection of duplicated regions between images. Traditional computer-vision based forensic models trained on natural images are not designed to overcome the challenges presented by biomedical images. We propose a multi-scale overlap detection model to detect duplicated image regions. Our model is structured to find duplication hierarchically, so as to reduce the number of patch operations. It achieves state-of-the-art performance overall and on multiple biomedical image categories.